Triple
T15584158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louis Székely |
E374574
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Alix Bailey |
E374581
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Alix Bailey | Statement: [Louis Székely, spouse, Alix Bailey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alix Bailey Context triple: [Louis Székely, spouse, Alix Bailey]
-
A.
Alix Bailey
chosen
Alix Bailey is an American painter and occasional actress best known for her work in the New York art scene and for her past marriage to comedian Louis C.K.
-
B.
Eloise Smyth
Eloise Smyth is a British actress best known for her role in the period drama television series "Harlots."
-
C.
Alice Dainard
Alice Dainard is a central teenage character in the science fiction film "Super 8," known for her emotional depth and involvement in the mysterious events surrounding a catastrophic train crash.
-
D.
Sarah Lea
Sarah Lea was the mother of English postal reformer Rowland Hill, noted primarily for her role in his early life and upbringing.
-
E.
Lily Smith
Lily Smith is an individual known primarily in relation to Megan Smith as a family member.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d85ccd575081908909b71a3f3e3a61 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e47971481909e986dd999354628 |
completed | April 16, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff56c5baac819099d53896f6a35d94 |
completed | May 9, 2026, 3:46 p.m. |
Created at: April 10, 2026, 4:11 a.m.